Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrist
    -0.06
     babys
    -0.06
     hostages
    -0.06
     ΑΓ
    -0.06
    nob
    -0.06
    _distances
    -0.06
    andum
    -0.06
    Singapore
    -0.06
     Psy
    -0.06
    URLRequest
    -0.06
    POSITIVE LOGITS
    isu
    0.07
     mlad
    0.07
    ?:
    0.06
    ıs
    0.06
    043
    0.06
     dříve
    0.06
     petit
    0.06
     Steam
    0.06
     Essay
    0.06
    تمع
    0.06
    Act Density 0.000%

    No Known Activations